Attributed Social Network Embedding

By Lizi Liao, Xiangnan He, Hanwang Zhang, Tat-seng Chua. IEEE Transactions on Knowledge and Data Engineering, 2017

417 citations recorded by the source corpus.

Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship networks and textual content of citation networks. These rich attribute information of social actors reveal the homophily effect, exerting huge impacts on the formation of social networks. In this paper, we explore the rich evidence source of attributes in social networks to improve network embedding. We propose a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors (i.e., nodes) by preserving both the structural proximity and attribute proximity. While the structural proximity captures the global network structure, the attribute proximity accounts for the homophily effect. To justify our proposal, we conduct extensive experiments on four real-world social networks. Compared to the state-of-the-art network embedding approaches, ASNE can learn more informative representations, achieving substantial gains on the tasks of link prediction and node classification. Specifically, ASNE significantly outperforms node2vec with an 8.2 percent relative improvement on the link prediction task, and a 12.7 percent gain on the node classification task.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/9f9966de50c7ab1c818b4330c9ec0b47994d62c6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shirui Pan
2. Chengqi Zhang
3. Guodong Long
4. Ugur Kursuncu
5. Jing Jiang
6. Manas Gaur
7. Amit P. Sheth
8. Xia Hu

In Information Systems

1. Jing Jiang
2. Guodong Long
3. Chang Zhou
4. Ugur Kursuncu
5. Manas Gaur
6. Hongxia Yang
7. Jie Tang
8. Yukuo Cen

In Statistical and Nonlinear Physics

1. Shirui Pan
2. Chengqi Zhang
3. Guodong Long
4. Ruiqi Hu
5. Jie Tang
6. Hongxia Yang
7. Jing Jiang
8. Rik Sarkar

Citations in the corpus

• AliGraph: A Comprehensive Graph Neural Network Platform (2019, background): “SNE [34] proposes a generic framework for embedding social networks by capturing both the structural proximity and attribute proximity.”
• Heterogeneous Graph Neural Network (2019, methodology): “Further, attributed graph embedding models [14, 15, 34] have been proposed to leverages both graph structure and node attributes for learning node embeddings.”
• Continuous-Time Dynamic Network Embeddings (2018, background): “Future work will investigate using the continious-time dynamic network framework to generalize heterogeneous network embedding methods [18] and attributed network embedding methods [38], among other approaches [26, 56].”
• Representation Learning for Attributed Multiplex Heterogeneous Network (2019, background): “Single Single Attributed LANE [16] AANE [15] SNE [20] DANE [9] ANRL [44]”
• Learning Graph Embedding With Adversarial Training Methods (2019, background): “SNE [36] learns a neural network model to capture both structural proximity and attribute proximity for attributed social networks.”
• Multi-scale Attributed Node Embedding (2019, methodology): “Many other methods exist, but do not consider the attributes of higher-order neighbourhoods [6, 7].”
• Deep Representation Learning for Social Network Analysis (2019, background): “this limitation, is to automatically learn feature representations that capture various information sources in networks (Bengio et al., 2013; Liao et al., 2018).”
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning (2021, methodology): “For instance, SNE [26] employs neural networks to model the interrelations between structure and attribute.”
• What's ur Type? Contextualized Classification of User Types in Marijuana-Related Communications Using Compositional Multiview Embedding (2018, background): “[6] proposed an approach to learn the interactional features of”